4 papers with code • 1 benchmarks • 1 datasets
( Image credit: SQL-to-Text Generation with Graph-to-Sequence Model )
Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings.
Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query.
We first design a SQL-to-text model conditioned on a sampled goal query, which represents a user's intent, that then converses with a text-to-SQL semantic parser to generate new interactions.